Text-to-Image
Diffusers
Safetensors
English
remote-sensing
earth-observation
satellite-imagery
flow-matching
diffusion-transformer
geospatial
Instructions to use BiliSakura/GeoCore-9B-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/GeoCore-9B-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/GeoCore-9B-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "A parking lot full of cars is located next to some trees." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download transformer/config.json from BiliSakura/GeoCore-9B-diffusers: direct link, hf CLI and curl.
- Browser
- Download file 494 Bytes
-
https://huggingface.co/BiliSakura/GeoCore-9B-diffusers/resolve/main/transformer/config.json
- Command line
-
hf download hf://BiliSakura/GeoCore-9B-diffusers/transformer/config.json
-
curl -L -o config.json https://huggingface.co/BiliSakura/GeoCore-9B-diffusers/resolve/main/transformer/config.json
494 Bytes
| { | |
| "_class_name": "GeoCoreTransformer2DModel", | |
| "_diffusers_version": "0.32.0", | |
| "in_channels": 128, | |
| "context_in_dim": 4096, | |
| "hidden_size": 4096, | |
| "num_heads": 32, | |
| "depth": 8, | |
| "depth_repa": 8, | |
| "depth_single_blocks": 24, | |
| "axes_dim": [ | |
| 32, | |
| 48, | |
| 48 | |
| ], | |
| "theta": 2000, | |
| "mlp_ratio": 3.0, | |
| "y_in_dim": 768, | |
| "z_out_dim": 4096, | |
| "model_size": "9b", | |
| "sample_size": 16, | |
| "patch_size": 2, | |
| "latent_channels": 128, | |
| "weights": "model", | |
| "training_steps": 300000 | |
| } | |